Optimization of neural network for nonlinear discrete time system using modified quaternion firefly algorithm: case study of Indian currency exchange rate prediction

Success of neural networks depends on an important parameter, initialization of weights and bias connections. This paper proposes modified quaternion firefly algorithm (MQFA) for initial optimal weight and bias connection to neural networks. The proposed modified quaternion firefly method is based on updating population, moving fireflies and best solution in quaternion space. The combination of modified quaternion firefly and neural network is developed with the scope of creating an improved balance between premature convergence and stagnation. The performance of the proposed method is tested on two nonlinear discrete time systems, Box–Jenkins time series data and exchange rate prediction of Indian currency. Results of the MQFA with back-propagation neural network (MQFA-BPNN) compared with existing differential evolution-based neural network and opposite differential evolution-based neural network. Results obtain using MQFA-BPNN envisage that this method is effective and provides better identification accuracy. Computational complexity of MQFA-BPNN is deliberated, and validation of proposed method is tested by statistical methods.

[1]  Driss Ouazar,et al.  Evolving neural network using real coded genetic algorithm for daily rainfall-runoff forecasting , 2009, Expert Syst. Appl..

[2]  Aderemi Oluyinka Adewumi,et al.  Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction , 2014, J. Appl. Math..

[3]  Tao Chen,et al.  Back propagation neural network with adaptive differential evolution algorithm for time series forecasting , 2015, Expert Syst. Appl..

[4]  Sheng Chen,et al.  Representations of non-linear systems: the NARMAX model , 1989 .

[5]  David Eberly,et al.  Quaternion Algebra and Calculus , 2002 .

[6]  John H. Conway,et al.  On Quaternions and Octonions , 2003 .

[7]  Xin-She Yang,et al.  Nature-Inspired Optimization Algorithms: Challenges and Open Problems , 2020, J. Comput. Sci..

[8]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[9]  Byung Ro Moon,et al.  A Hybrid Neurogenetic Approach for Stock Forecasting , 2007, IEEE Transactions on Neural Networks.

[10]  Shaocheng Tong,et al.  Adaptive Fuzzy Robust Output Feedback Control of Nonlinear Systems With Unknown Dead Zones Based on a Small-Gain Approach , 2014, IEEE Transactions on Fuzzy Systems.

[11]  P. Girard,et al.  The quaternion group and modern physics , 1984 .

[12]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[13]  Amjad Alipanah,et al.  Nonclassical Pseudospectral Method for a Class of Singular Boundary Value Problems Arising in Physiology , 2012 .

[14]  Nader Sadegh,et al.  A perceptron network for functional identification and control of nonlinear systems , 1993, IEEE Trans. Neural Networks.

[15]  Yanqing Zhang,et al.  Statistical fuzzy interval neural networks for currency exchange rate time series prediction , 2007, Appl. Soft Comput..

[16]  Tugrul U. Daim,et al.  Using artificial neural network models in stock market index prediction , 2011, Expert Syst. Appl..

[17]  Shuzhi Sam Ge,et al.  Robust Adaptive Neural Network Control for a Class of Uncertain MIMO Nonlinear Systems With Input Nonlinearities , 2010, IEEE Transactions on Neural Networks.

[18]  Yaman Arkun,et al.  Control of nonlinear systems using polynomial ARMA models , 1993 .

[19]  Jonathan L. Ticknor.  A Bayesian regularized artificial neural network for stock market forecasting , 2013, Expert Syst. Appl..

[20]  Adel Belouchrani,et al.  Estimation of Multicomponent Polynomial-Phase Signals Impinging on a Multisensor Array Using State–Space Modeling , 2007, IEEE Transactions on Signal Processing.

[21]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[22]  Tommy W. S. Chow,et al.  A weight initialization method for improving training speed in feedforward neural network , 2000, Neurocomputing.

[23]  Grigorios N. Beligiannis,et al.  Combining evolutionary and stochastic gradient techniques for system identification , 2009 .

[24]  Wei Huang,et al.  The Criticality of Spare Parts Evaluating Model Using Artificial Neural Network Approach , 2006, International Conference on Computational Science.

[25]  Kumpati S. Narendra,et al.  Identification and control of a nonlinear discrete-time system based on its linearization: a unified framework , 2004, IEEE Transactions on Neural Networks.

[26]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[27]  Uday Pratap Singh,et al.  FCPN Approach for Uncertain Nonlinear Dynamical System with Unknown Disturbance , 2017, Int. J. Fuzzy Syst..

[28]  Masahiro Abe,et al.  Incipient fault diagnosis of chemical processes via artificial neural networks , 1989 .

[29]  Jian Li,et al.  Multistatic Adaptive Microwave Imaging for Early Breast Cancer Detection , 2006, IEEE Transactions on Biomedical Engineering.

[30]  Tianyou Chai,et al.  A Nonlinear Control Method Based on ANFIS and Multiple Models for a Class of SISO Nonlinear Systems and Its Application , 2011, IEEE Transactions on Neural Networks.

[31]  Tsu-Tian Lee,et al.  The Chebyshev-polynomials-based unified model neural networks for function approximation , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[32]  Janez Brest,et al.  Modified firefly algorithm using quaternion representation , 2013, Expert Syst. Appl..

[33]  Xin-She Yang,et al.  Engineering Optimization: An Introduction with Metaheuristic Applications , 2010 .

[34]  Yonggui Kao,et al.  A Fuzzy Control Approach to Stabilization of Markovian Jump Systems with General Unknown Transition Probabilities , 2016, Int. J. Fuzzy Syst..

[35]  Grigorios N. Beligiannis,et al.  Nonlinear model structure identification of complex biomedical data using a genetic-programming-based technique , 2005, IEEE Transactions on Instrumentation and Measurement.

[36]  H Gholam Hosseini,et al.  The comparison of different feed forward neural network architectures for ECG signal diagnosis. , 2006, Medical engineering & physics.

[37]  S. C. Tong,et al.  Adaptive Neural Network Decentralized Backstepping Output-Feedback Control for Nonlinear Large-Scale Systems With Time Delays , 2011, IEEE Transactions on Neural Networks.

[38]  Marjan Mernik,et al.  Analysis of exploration and exploitation in evolutionary algorithms by ancestry trees , 2011 .

[39]  Bidyadhar Subudhi,et al.  A differential evolution based neural network approach to nonlinear system identification , 2011, Appl. Soft Comput..

[40]  R.J. Cohen,et al.  Linear and nonlinear ARMA model parameter estimation using an artificial neural network , 1997, IEEE Transactions on Biomedical Engineering.

[41]  Rasoul Irani,et al.  Evolving neural network using real coded genetic algorithm for permeability estimation of the reservoir , 2011, Expert Syst. Appl..

[42]  Michael R. Lyu,et al.  A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training , 2007, Appl. Math. Comput..

[43]  Rodney A. Stewart,et al.  ANN-based residential water end-use demand forecasting model , 2013, Expert Syst. Appl..

[44]  Li Zhang,et al.  An evaluation of back-propagation neural networks for the optimal design of structural systems: Part I. Training procedures , 2002 .

[45]  G. Dixon,et al.  On quaternions and octonions: Their geometry, arithmetic, and symmetry , 2004 .